Diversity as a Reward: Fine-Tuning LLMs on a Mixture of Domain-Undetermined Data
Fine-tuning large language models (LLMs) using diverse datasets is crucial for enhancing their overall performance across various domains. In practical scenarios, existing methods based on modeling the mixture proportions of data composition often struggle with data whose domain labels are missing, imprecise or non-normalized, while methods based on data selection usually encounter difficulties in balancing multi-domain performance. To address these challenges, in this paper, we study the role of data diversity in enhancing the overall abilities of LLMs by empirically constructing contrastive data pools and theoretically deriving explanations for both inter- and intra-diversity. Building upon the insights gained, we propose a new method that gives the LLM a dual identity: an output model to cognitively probe and select data based on diversity reward, as well as an input model to be tuned with the selected data. Extensive experiments show that the proposed method notably boosts performance across domain-undetermined data and a series of foundational downstream tasks when applied to various advanced LLMs. We release our code and hope this study can shed light on the understanding of data diversity and advance feedback-driven data-model co-development for LLMs.
Code (1)
Tasks
DiversitySimilar Papers 제목 키워드 기반
MoDoMoDo: Multi-Domain Data Mixtures for Multimodal LLM Reinforcement Learning
Reinforcement Learning with Verifiable Rewards (RLVR) has recently emerged as a powerful paradigm for post-training large language models (LLMs), achieving state-of-the-art performance on tasks with structured, verifiabl…
GFlowNet Fine-tuning for Diverse Correct Solutions in Mathematical Reasoning Tasks
Mathematical reasoning problems are among the most challenging, as they typically require an understanding of fundamental laws to solve. The laws are universal, but the derivation of the final answer changes depending on…
DiversityMathematical ReasoningReinforcement Learning (RL)Process-Supervised LLM Recommenders via Flow-guided Tuning
While large language models (LLMs) are increasingly adapted for recommendation systems via supervised fine-tuning (SFT), this approach amplifies popularity bias due to its likelihood maximization objective, compromising …
DiversityFairnessRecommendation SystemsEfficient Diversity-Preserving Diffusion Alignment via Gradient-Informed GFlowNets
While one commonly trains large diffusion models by collecting datasets on target downstream tasks, it is often desired to align and finetune pretrained diffusion models with some reward functions that are either designe…
DiversityOn the Modeling Capabilities of Large Language Models for Sequential Decision Making
Large pretrained models are showing increasingly better performance in reasoning and planning tasks across different modalities, opening the possibility to leverage them for complex sequential decision making problems. I…
Decision MakingDiversityReinforcement Learning (RL)Sequential Decision Making